• Nie Znaleziono Wyników

The Bias of Estimators of Models with Errors in Variables

N/A
N/A
Protected

Academic year: 2021

Share "The Bias of Estimators of Models with Errors in Variables"

Copied!
10
0
0

Pełen tekst

(1)

A C T A U N I V E R S I T A T I S L O D Z I E N S I S FOLIA OECONOMICA 9 0 , 19 89______________________

# H a l i n a K l e p a o z

THE BIAS OF ESTIMATORS OF MODELS WITH ERRORS IN VARIABLES

1. INTRODUCTION

The m ain s u b j e c t o f t h i s p a p e r a r e e s t i m a t o r s o f p a r a m e t e r s o f o n e - e q u a t i o n l i n e a r m o d e l s w i t h e r r o r s i n e x o g e n o u s v a r i a b l e s . The known a n a l y s e s w e r e c o n c e n t r a t e d o n , a s f o r t h e c l a s s o f mo-d e l s u n mo-d e r i n v e s t i g a t i o n , t h e c o m p a r i s o n o f a s y m p t o t i c mean s q u -a r e e r r o r s o f c h o s e n e s t i m a t o r s a c c o r d i n g t o d i f f e r e n t e s t i m a -t i o n m e -t h o d s .

From t h e o r e t i c a l and p r a c t i c a l p o i n t s o f v i e w t h e small samp-l e f e a t u r e s o f e s t i m a t o r s f o r t h e e r r o r s i n v a r i a b l e s m o d e l s a r e a l s o i m p o r t a n t . A p r a c t i c i o n e r i s i n t e r e s t e d i n t h e c o n d i t i o n s o f a p p l y i n g s p e c i a l e s t i m a t i o n m e t h o d s . I f we s t u d y t h e se m e t h o d s i n t e r m s o f mean s q u a r e e r r o r e q u a l t o t h e sum o f b i a s s q u a r e and v a r i a n c e t h e n , k n o w in g t h e s i z e o f t h e b i a s o f p a r a m e t e r e s -t i m a -t e s o f t h e m o d e l d e s c r i b i n g t h e r e s u l t s o f o b s e r v a t i o n s w i t h m e a s u r e m e n t e r r o r s I s a b s o l u t e l y n e c e s s a r y . The p a p e r c o n t a i n s t h e a n a l y s i s o f b i a s e s o f t h e c h o s e n e s -t i m a -t e s o f -t h e -t h r e e v e r s i o n s o f t h e m o d e l : 1) w i t h tw o e x o g e n o u s v a r i a b l e s , o n e o f w h i c h i s m e a s u r e d w i t h e r r o r ; * L e c t u r e r i n th£ I n s t i t u t e o f E c o n o m e tr ic s and S t a t i s t i c s , U n i v e r s i t y o f Łódź.

1 F or th e model w ith one e x p l a n a t o r y v a r i a b l e measure d w i t h e r r o r , th e a n a l y s i s of r e s u l t s o f t h e tlonte C a r lo e x p e r i m e n t was p r e s e n t e d in [1 j ,

(2)

2) w i t h t h r e e e x p l a n a t o r y v a r i a b l e s , o n e o f w h i c h h a s t h e n e a s u r e m e n t e r r o r ; 3 ) w i t h t h r e e e x p l a n a t o r y v a r i a b l e s , t w o o f w h i c h a r e o b s e r v e d w i t h e r r o r . The a n a l y s i s i s c o n d u c t e d on t h e b a s i s o f t h e r e s u l t s o f Mon-2 t e C a r l o e x p e r i m e n t s f o r c h o s e n s i r e t h o d s , t h e s a m p l e s i z e s , c o e f f i c i e n t o f d e t e r m i n a t i o n , t h e e r r o r s o f t h e m e a s u r e m e n t o f v a r i a b l e s and t h e c o r r e l a t i o n c o e f f i c i e n t b e t w e e n t h e e x p l a n a t o r y v a r i a b l e s .

e-2. STEERINC VARIABLES AND PARAMETERS ACCEPTED IN THE EXPERIMENTS

We w i l l a n a l y s e t h e b i a s e s o f t h e e s t i m a t o r s o f t h e m o d i f i e d l e a s t s q u a r e s m e th o d ( O L S ) , o f t h e Maximum l i k e l i h o o d m eth od ( m l m ) , o f t h e i n s t r u m e n t a l v a r i a b l e s m e t h o d s : by Wald

(IV

WAL), B a r t l e t t

(IV

BAR) and D u r b i n

(IV

DUR). T h e s e b i a s e s w e r e c a l c u

-l a t e d an d co m p a re d f o r t h r e e v e r s i o n s o f o n e - e q u a t i o n , l i n e a r mo-d e l [1] w i t h e r r o r s i n e x p l a n a t o r y v a r i a b l e s , i . e . Yi о a и + a 1 + *li + a 3X3 i ( E i - “ 3V3i> (1) Yi = a G+ a1X 1 i + a2X2 i + a 3X3 i + ( с А - a3V3 i ) C2) Yi = u 0 + a1X1i + a2X2i + a 3 X3 i + ( E l - a2V21 - a3V3 i ) ( 3 ) I n s t e a d o f u n o b s e r v a b l e e x p l a n a t o r y v a r i a b l e X, t h e o b -^ / J s e r v a L l e X^ 3 i s i n t r o d u c e d i n t h e s e m o d e l s . Random v a r i a b l e V^ e x p r e s s i n g t h e m e a s u r e m e n t e r r o r s o f t h e X_. , i s n o r m a l l y o i s t r i b u t e d w i t h e x p e c t e d v a l u e Е(У^) = 0 and v a r i a n c e •у 2 D (Vj') = O’ j , j = 2 , 3 . M o r e o v e r , i t i s a ssu m e d t h a t : E ( e / v ) = = E ( c ) = 0 ,

E (Y /v)

=

Xa

a n d

X

i s t h e m a t r i x o f o b s e r v a t i o n s В (e e T/ v ) = в 2I .

The construction of the sandle space was dis cu ssed in [3] the re-view of estim atio n methods fo r the models with measurement errors are given

(3)

3 V a r i a b l e s a r e t r e a t e d i n e x p e r i m e n t s a s f i x e d o n e s , b e i n g r e p e a t e d i n a l l e x p e r i m e n t r e p e t i t i o n s . I n t h e e x p e r i m e n t s t h a t h a v e b e e n c a r r i e d o u t , t h e number o f o b s e r v a t i o n s I n a s a m p l e w as f i x e d a t t h e l e v e l s n = 20 , 30, 40, 5U ( o b s e r v a t i o n s f o r w e r e c h o s e n a s t h e f i r s t n e l e m e n t s from t h e c n o s e n colum n o f a t a b l e o f random n u m b e r s ) . The v a -l u e s o f s t r u c t u r a -l p a r a m e t e r s o f t h e m o d e l s (1) - ( 3 ) w e r e f i x e d a t t h e l e v e l ! = 1000 , = 3 , = 2 . The c h o i c e o f a g i v e n v e c t o r o f s t r u c t u r a l p a r a m e t e r s i s l i m i t i n g t h e r a n g e o f r e a s o n i n g t o t h e g i v e n s t r u c t u r e o f l i n e a r m o d e l w i t h e r r o r s - - i n - v a r i a b l e s . The d i r e c t i o n s o f c h a n g e s o f e s t i m a t i o n b i a s e s and t h e q u a n t i t i e s o f t h e s e b i a s e s d e p e n d on t h e s i z e o f t h e s a m p l e a n a s t o c h a s t i c s t r u c t u r e o f t h e c h o s e n m o d e l s . 2 The f o l l o w i n g l e v e l s w e r e a c c e p t e d ! P = 0 . 5 0 ; 0 . 6 0 ; 0 . 7 0 ; J .d O ; 0 . 9 0 ; 0 . 9 5 ; 0 . 9 9 and t h e RB l e v e l s , i . e . t-he q u o t i e n t o f t h e e r r o r v a r i a n c e and t h e s a m p l e v a r i a n c e o f a g i v e n e x -p l a n a t o r y v a r i a b l e : 0 . 0 1 ; 0 . 0 5 ; 0 . 1 0 ; 0 , 1 5 .

3. THE BIASES OF ESTIMATORS OF CHOSEN METHODS

IN DEPENDENCE ON THE SAMPLE SU E AS I) THE ERRORS OK MEASUREMENT

л е s h a l l a n a l y s e now t h e i n f l u e n c e i f t h e e n l a r g i n g o f e x -p l a n a t o r y v a r i a b l e s i n t h e m o d e l on t h e b i a s e s o f t h e n a r a m e t e r e s t i m a t i o n s o f t h e m o d e l s w i t h e r r o r s i n t h e v a r i a b l e s . I t s h o u l d b e rem em bered t h a t t h e i n c r e a s e o f v a l u e s o f RB 4 e r r o r i n t h e m odel w i t h o n e e x p l a n a t o r y v a r i a b l e m e a s u r e d w i t h e r r o r c a u s e d a l m o s t p r o p o r t i o n a l i n c r e a s e o f t h e a v e r a g e b i a s e s . I t was o b s e r v e d i n r e l a t i o n t o t h e r e t h o d w h i c h we may c a l l " b a s i c " a s f u r t h e r we s h a l l co m p a re t h e r e s u l t s o b t a i n e d by t h i s m e t h o d w i t h o t h e r s . The e n l a r q i n g o f t h e m o d e l by a d d i n g an ad-d i t i o n a l v a r i a b l e m e a s u r e d w i t h o u t e r r o r , c a u s e s s i m i l a r t e n d e n -c y , b u t , f o r e a c h t e s t e d m e t h o d , e x c e p t t h e LSM and MLM, we o b -s e r v e t h e d e c r e a -s e i n b i a s e s o f t h e a v e r a q e e s t i m a t e s o f p a r a -The se q u e n c e s of th e v a r i a b l e v a lu e « t a k e n from [4 ]. 4

The a n a l y s i s o f Monte C a r lo e x p e r i m e n t f o r th e model Y. = «q + +

(4)

r f i e t e r s , f o r t h e m o d e l s w i t h v a r i a b l e m e a s u r e d w i t h e r r o r s ( s e e T a b l e O . T a b l e 1 Average b i a s e s of t h e p a r a m e t e r e s t i m a t e s of th e models ( 0 - ( 2 ) i n r e l a t i o n t o t h e a v e r a g e e s t i m a t e s o f t h e b a s i c method f o r n - 20 and R2 - 0 . 9 9 , IP - 500 Rfl Methods Average b i a s e s ( i n %) f o r t h e model w i t h a one v a r i a b l e u 3 ) b two v a r i a b l e s three*5 v a r i a b l e s ( x 3 ) ( X , ) ( x 3 ) ( x , ) ( x 2 ) LSM - 4 . 4 - 3 . 5 0 . 6 - 3 . 3 0 . 6 - 0 . 7 OLS 0 . 6 1.5 - 0 . 5 1 .8 - 0 . 2 0 -5 0 . 0 5 MLM 0 . 7 1 .8 - 0 . 2 2.1 - 0 . 3 0 . 6 IV DUR - 3 . 7 - 3 . 7 0 . 6 - 3 . 5 0 . 7 - 0 . 8 LSM - 8 . 2 - 7 . 1 1.1 - 6 . 8 1. 3 - 1 . 6 OLS 1.4 2 . 8 - 0 . 2 3 . 4 - 0 . 4 0 . 2 0 . 10 MLM 1 . 8 3 .4 - 0 . 4 4 . 0 - 0 . 6 1.2 IV DUR - 7 . 6 - 7 . 1 1.1 ■ - 6 . 8 1.3 - 1 . 6 LSM - 1 1 . 4 - 1 0 . 6 - 1 0 . 6 - 1 0 . 0 1.9 - 2 Л OLS 2 .2 3 .7 - 0 . 3 5 .3 - 0 . 5 0 . 9 0 . 13 MLM 2.7 5 .0 - 0 . 6 6 . 0 - 1 . 0 1 . 7 V IV DUR - 1 0 . 3 - t o . 1 - 1 . 6 - 9 . 7 1 .8 - 2 . 3

a The r e s u l t s g iv e n in t h i s column a r e t a k e n from [ 3 ] .

^ The c o n s t r u c t i o n o f t h e sam ple s p a c e was d i s c u s s e d i n [ 3 ] t h e rev iew o f e s t i m a t i o n methods f o r t h e models w i t h mea sure m ent e r r o r s a r e g i v e n in [ 1j, [2]. \

,

A v e r a g e e s t i m a t e s o f t h e p a r a m e t e r s f o r s u c h m o d e l s a r e a l s o b i a s e d a l t h o u g h t h e c h a n g e o f t h e b i a s d i r e c t i o n i s i n t h e s m a l l d e g r e e , a c h a r a c t e r i s t i c f e a t u r e o f t h e s e b i a s e s , i . e . i f i n a g i v e n m e th o d we u n d e r e s t i m a t e p a r a m e t e r s w i t h t h e v a r i a b l e m e a s -u r e d w i t h e r r o r , t h e n t h e a v e r a g e v a l u e o f e s t i m a t o r w i t h " n o - - e r r o r " v a r i a b l e i s o v e r e s t i m a t i n g p a r a m e t e r and v i c e v e r s a . The i n t r o d u c t i o n o f a n o t h e r " n o - e r r o r “ v a r i a b l e t o t h e m o d e l (1) c a u s e s r a t h e r s m a l l i n c r e a s e i n t h e a b s o l u t e a v e r a g e b i a s e s

/

(5)

o f t h e p a r a m e t e r e s t i m a t e s w i t h t h e f i r s t " n o - e r r o r " v a r i a b l e and t h e d i m i n i s h i n g o f t h e a v e r a g e b i a s e s o f e s t i m a t o r s i n t h e same d i r e c t i o n , w i t h t h e v a r i a b l e m e a s u r e d w i t h e r r o r ( e x c e p t OLS and LSM m e t h o d s , w h e r e t h e t e n d e n c y i s t h e o p p o s i t e o n e ) . I f we i n t r o d u c e a d d i t i o n a l l y t o t h e m o d e l ( 1 ) a v a r i a b l e m e a s u r e d w i t h e r r o r ( i n s t e a d o f " n o e r r o r “ o n e ) , t h e n t h e i n c r e a -s e i n b i a -s e -s c a n b e o b s e r v e d f o r t h e e s t i m a t e s o f b o t h p a r a -m e t e r s . The b i g g e r RB f o r t h e i n t r o d u c e d v a r i a b l e i s , t h e g r e a t -e r t h -e i n c r -e a s -e i n b i a s -e s w i l l b -e . The i n c r e a s e i n t h i s b i a s i s n o t v e r y b i g f o r t h e p a r a -m e t e r s e s t i m a t e w i t h t h e f i r s t v a r i a b l e m e a s u r e d w i t h e r r o r and b i g f o r p a r a m e t e r e s t i m a t e s w i t h t h e v a r i a b l e m e a s u r e d w i t h -o u t e r r -o r . T h i s b i a s I n c r e a s e q u i c k l y t o g e t h e r w i t h t h e i n -c r e a s e o f t h e RB l e v e l ( s e e T a b l e 2 ) , an d t h e i n c r e a s e o f e a c h m e a s u r e m e n t e r r o r o f RB c a u s e s t h e i n c r e a s e o f a l l t h e b i a s e s . T a b l e 2 Average b i a s e s o f t h e p a r a m e t e r e s t i m a t e s o f t h e model ( 3 ) i n r e l a t i o n t o th e a v e r a g e e s t i m a t e s o f t h e b a s i c method f o r n ■ 20 and R2 " 0 .9 9 RB2 Methods Average b i a s e s o f t h e p a r a m e t e r e s t i m a t e s f o r RBI » 0 .0 5 RBI - 0 .1 5 “ l a 2 a 3 a 1 a 2 a 3 LSM 1.3 - 5 . 1 - 3 . 9 2 . 5 - 1 3 . 6 - 4 . 3 OLS - 0 . 4 2 .2 1.6 - 0 . 8 5 .4 1.7 0 . 0 5 MLM - 0 . 6 2 .9 1.7 - 1 . 3 7 .2 1.9 IV DUR 1 .5 - 6 . 2 1 ■*> *o 2 . 5 - 1 3 . 0 - 4 . 3 LSM 1.9 - 6 . 0 - 7 . 5 3 . 2 - 1 4 . 5 - 7 . 9 OLS - 0 . 6 2 . 7 2 . 8 - 1 . 5 7 .3 3 . 2 0 . 10 MLM - 0 . 9 3 . 3 3 . 4 - 1 . 6 7 .7 3 .7 IV DUR 2.1 - 7 . 3 - 7 . 4 3 . 2 - 1 4 . 9 / - 7 . 7 LSM 2 . 5 - 6 . 8 - 1 0 . 8 3 . 8 - 1 5 . 3 - 1 1 . 2 OLS - 0 . 9 3 .3 3 . 4 - 1 . 6 7.6 3 , 8 0 . 1 5 MLM - 1 . 2 4 .0 5 . 3 - 1 . 9 8 .3 5 . 7 IV DUR 2 .7 - 8 . 4 - 1 0 . 3 3 .7 - 1 5 . 8 - 1 0 . 6 '

(6)

I n LSM IV DUR m e t h o d s t h e i n t r o d u c t i o n o f an a d d i t i o n a l v a r i a b l e ( w i t h o r w i t h o u t e r r o r ) c a u s e s t h e u n d e r e s t i m a t i o n o f t h e e s t i -m ate when a v a r i a b l e i s m e a s u r e d w i t h e r r o r а з w e l l a s f o r t h e i n t r o d u c e d v a r i a b l e ? w h i l e i n OLS and MLM m e t h o d s t h e r e c a n be o b s e r v e d t h e o v e r e s t i m a t i o n o f a v e r a g e p a r a m e t e r e s t i m a t e s and i t s a b s o l u t e v a l u e i s s m a l l e r t h a n f o r LSM a n d IV DUR. T a b l e 3 Average b ia s e s ( i n of the parameter estim ates

of the model ( 3 ) in r e la t io n to the average estim ates of the b a s ic method in r e l a t i o n t o the measurement errors of the explanatory v a r ia b le s for n * 20, R2 ■ 0 . 9 5 , IP “ 500

Estimated

Rhl RB2

Methods of es tim atio n parameter

LSM OLS MIX IV DUR

0.01 1.3 -0.6 -0.8 1 .3 0.05 1.8 - 0 . 9 -1.0 1.9 0. 10 0. 10 2.5 -1.2 - 1 . 4 2.6 0. 15 3.2 - 1 . 4 - 1 . 7 3.3 “ l 0.01 1.3 —06 - 0 . 7 1.4 0.05 1.9 - 0 . 9 -1.0 2.0 0.10 0. 10 2.5 - 1 . 3 - 1 . 4 2.6 0.15 3.1 - 1 . 5 - 1 . 7 3.1 0.01 - 7 . 9 3.4 5 .5 - 8 . 9 0.05 - 8 . 7 3.9 5 . 8 - 9 . 8 0. 10 0.10 - 9 . 5 4.2 6.3 - 1 0 .9 0. 15 -12.0 5 .6 7.3 -1 3 .7 • a2 0.01 - 2 . 3 1.1 1.6 - 3 . 7 0 .0 5 - 5 . 5 2. В 3 . 8 - 7 . 4 0. 10 0. 10 - 9 . 5 4.9 6.3 -1 0 .9 0. 15 - 1 3 .3 7.6 8.9 -1 3 .5 0.01 -1.1 0 .3 -0.6 -1.1 0.05 - 4 .1 1.6 1.9 -4 .1 0.10 0.10 - 7 . 6 3. 1 3.6 - 7 . 5 0. 15 -11.0 4.9 5.6 -1 0 .4 “ 3 0.01 - 7 . 2 2.8 3.4 - 7 . 4 0.05 - 7 . 4 2.9 3.5 - 7 . 3 0.10 0. 10 - 7 . 6 3. 1 3 .6 - 7 . 5 0.15 - 7 . 8 3.2 3 . 8 - 7 . 6

(7)

A v e r a g e b i a s e s o f t h e p a r a m e t e r e s t i m a t e s f o r t h e m o d e l ( 3 ) i n r e l a t i o n t o t h e a v e r a g e p a r a m e t e r e s t i m a t e s o f t h e b a s i c m e t h -od d e p e n d more on RB t h a n on t h e c h a n g e s o f d e t e r m i n a t i o n c o e f -f i c i e n t . T h i s i s i l l u s t r a t e d by t h e T a b l e s 3 and 4 . H o w e v e r , we 2 o b s e r v e t h a t t o g e t h e r w i t h t h e i n c r e a s e o f R t h e b i a s e s o f p a r a m e t e r e s t i m a t e s OLS and MLM d e c r e a s e and t h e b i a s e s o f t h e e s t i m a t e s f o r o t h e r m eth od i n c r e a s e .

T a b l e 4 Average b ia s e s of the parameter estim ates

for the model (3,) in relatwm

to the average c'Stimates of the b a sic method fo r RBI - 0 . 0 5 , RB2 - 0 . 1 0 , n “ 20, IP - 500 Estimated parumeter Method of estima-tion Assumed values of co r r e la t io n c o e f f i c i e n t 0 . 5 0.6 0.7 0.8 0.9 0.95 0.99 LSM 1 .3 1.4 . 1.6 1.7 1.8 1.9 1.9 * OLS - 1 . 3 - 1 .3 -1.2 -1.1 1.0 - 0 . 9 -0.8 “ l MLM - 1 . 5 - 1 .4 - 1 . 3 - 1 . 3 -1.1 -1.0 - 0 .9 IV DUR 1.4 1.5 1.7 1.9 2.0 2.0 2.1 1 IV WAL 0 . 4 0 .5 0 . 7 0. 7 0.8 0.9 0 .9 IV BAR 0.8 1.0 1.2 1.4 1.5 1.6 1.6 LSM - 3 . 7 - 4 . 2 - 4 . 8 - 4 . 8 - 5 .1 - 5 . 5 , -6.0 OLS 5.1 4.8 4.2 3 . 8 3.3 2.8 2.7 a 2 MLM 5.3 5. 1 4.7 4 .3 4. 1 3 .8 3.3 IV DUR - 4 . 9 1 CO -6.1 - 6 . 3 - 6 . 7 - 7 . 4 - 7 . 3 IV WAL 1.6 0.9 0 .5 0.2 0. 1 -0.2 - 0 . 5 IV BAR - 3 . 2 - 4 . 3 -5.1 - 5 .7 -6.2 - 6 . 4 LSM - 6 . 9 - 7 . 1 - 7 . 2 - 7 . 1 - 7 . 3 - 7 . 4 - 7 . 5 OLS 3 .6 3.5 3.4 3.4 3.1 2.9 2.8 a 3 MLM 3 . 8 3.7 3.7 3.7 3.5 3.5 3 .4 IV DUR - 6 . 7 -6.8 -6 .9 - 7 .1 - 7 . 2 - 7 .3 - 7 . 4 IV WAL - 6 . 3 -6. 1 - 5 . 8 - 5 . 6 - 5 . 3 - 5 .1 - 4 . 8 IV BAR - 4 . 8 - 5 . 1 - 5 . 3 - 5 . 6 - 5 . 8 -6.0 - 6 . 3 The i n c r e a s e o f t h e s a m p l e s i z e I s e e : T a b l e 1 and 5 ) d o e s n o t c a u s e t h e d e c r e a s e i n b i a s e s e i t h e r i n LSM o r i n XV DUR.This d e c r e a s e i s o b s e r v e d f o r OLS and 'LLM m e t h o d s .

(8)

T a b l e 5 Average b ia s e s of the parameter estim ates

o f the model (2) in r e la t io n

t o the average estim ates of the b a s ic method for RBI “ 0.10 and n “ 50, IP ■ 500

RB2 Method

Assumed value o f the determination c o e f f i c i e n t 0.90 0.95 0.99 *1 *2

x3

*1 *2 *3 Xt x2

x3

LSM 0.8 - 1 . 4 - 4 .6 0.8 - 1 . 3 - 4 . 6 0.8 - 1 . 3 - 4 . 6 OLS 0.0 0.2 0 .5 0.0 0.2 0 .5 0.0 0.2 0.6 0.05 MLM 0.0 0.2 0 .5 0.0 0.2 0 .5 0.0 0.2 0.6 IV DUR 0 .7 - 1 . 7 - 4 . 4 0 .7 - 1 . 3 - 4 . 3 0 .7 - 1.2 - 4 . 3 LSM 1.5 - 2 . 7 - 8 .9 1.4 -2.6 -8.8 1.5 - 2 . 5 -8.8 OLS -0. 1 0 .3 1.1 -0.1 0 .3 1.1 -0.1 0 .4 1.1 0. 10 MLM -0.1 0 .3 1.1 -0.1 0 . 4 1.1 -0.1 0 . 4 1.2 IV DUR 1.4 - 2 . 5 -8.2 1.4 - 2 . 4 -8.2 1.4 - 2 . 3 -8.1 LSM 2. 1 - 3 . 9 -12.8 2.1 - 3 . 8 - 1 2 .7 2.1 - 3 . 7 -12.6 OLS -0.2 0 .5 1.6 -0.2 0 .5 1.6 0.2 0 .5 1.6 0. 15 MLM -0.2 0 . 5 1.6 -0.2 0.6 1.7 -0.2 0.6 1.8 IV IX!R 2.0 - 3 . 6 -11.8 1.9 - 3 .5 - 1 1 .7 1.9 - 3 . 3 -11.6 We c a n o b s e r v e s i g n i f i c a n t i n f l u e n c e o f t h e d e g r e e o f c o r r e -l a t i o n b e t w e e n t h e e x p l a n a t o r y v a r i a b l e s m e a s u r e d w i t h o u t any e r r o r on t h e b i a s e s o f p a r a m e t e r e s t i m a t e s o f t h e m o d e l s ( s e e T a b l e 6) . The i n c r e a s e o f t h e d e g r e e o f v a r i a b l e c o r r e l a t i o n c a u s e s t h e i n c r e a s e o f b i a s e s f o r b o t h t h e p a r a m e t e r e s t i m a t e s m e a s u r e d w i t h and w i t h o u t e r r o r . The a b s o l u t e v a l u e o f e s t i m a t o r s b i a s i s g r e a t e r when t h e v a r i a b l e i s m e a s u r e d w i t h e r r o r . C on-s i d e r i n g t h e b i a on-s e on-s i n d i f f e r e n t m e t h o d s o f e s t i m a t i o n we c a n s t a t e t h a t OLS and MLM a r e f a r b e t t e r t h a n t h e o t h e r s and I V - - m e t h o d s a r e n o t " b ę t t e r " t h a n o r i d i n a r y l e a s t s q u a r e s m e t h o d i f i n s a m p l e s o f 20 e l e m e n t s t h e c o r r e l a t i o n c o e f f i c i e n t s i n c r e a s e . O u ic k r e a c t i o n o f t h e IV WAL m e th o d on t h e i n c r e a s e o f t h e v a l u -e s o f t h -e c o r r -e l a t i o n c o -e f f i c i -e n t l -e a d i n g t o l a r g e b i a s e s when c o r r e l a t i o n c o e f f i c i e n t ę?i s l a r g e i s v e r y a l a r m i n g .

(9)

T a b l e 6 Average b ia se s of the parameter estim ates

of the model ( l ) in r e la t io n to average estim ates of the b a s ic method

for n - 2 0 , RJ - 0 . 9 5 , RB - 0 .5 in dependence on the degree of c or re lation

of the explanatory v a r ia b le s IP " 500 Estimated parameter Cor re 1 a- tion c o e f f i -cient

Method of estim ation

LSM OLS MLM IV DUR IWAL IV BAR

0.03 0.1 -0.0 0.0 0. 1 0. 1 0.1 0.45 0 .5 -0. 1 -0.2 0.6 0.6 0.7 a 2 0.70 1.1 - 0 . 4 -0.6 1.4 2.7 1.6 0.88 3. 1 - 1 . 7 -2.0 3.3 21.8 3.7 0.03 - 3 . 3 1.4 1.7 - 3 . 5 - 2 . 7 - 3 . 3 0.45 - 4 . 0 1.9 2.2 - 4 . 6 - 4 . 1 , - 5 . 2 a 3 0.70 -6.8 3.1 3.5 - 7 . 9 -1 5 .7 - 9 .1 0.88 - 1 3 .3 7.9 8.7 -1 3 ,6 -2 6 .5 - 1 6 .4 On t h e b a s i s o f t h e c a r r i e d o u t e x p e r i m e n t s we c a n c o n c l u d e t h a t t h e more " n o - e r r o r " v a r i a b l e s we h a v e i n t h e m o d e l , t h e s m a l l e r t h e a v e r a g e b i a s e s o f t h e e s t i m a t e s c o v e r i n g p a r a m e t e r s s t a n d i n g n e a r b y a v a r i a b l e m e a s u r e d w i t h e r r o r a r e i n LSM and IV DUR. I f t h e v a r i a b l e i s m e a s u r e d w i t h o u t e r r o r , t h e r e e x i s t h a r d l y o b s e r v a b l e b i a s e s . The o p p o s i t e s i t u a t i o n t a k e s p l a c e i n t h e c a s e o f e n l a r g i n g o f t h e m o d e l w i t h v a r i a b l e s t r e a s u r e d w i t h e r r o r . 2 T h e r e ca n a l s o b e n o t i c e d i n s i g n i f i c a n t i n f l u e n c e o f R and t n e s a m p l e s i z e on a v e r a g e b i a s e s o f t h e p a r a m e t e r e s t i m a t e s i n r e l a t i o n t o t h e b a s i s n e t h o d , i . e . t o t h e m o d e l w h e r e a l l t h e v a r i a b l e s a r e o b s e r v e d w i t h o u t e r r o r . 4. FURTHER INVESTIGATIONS The p r e s e n t e d a n a l y s i s o f b i a s e s o f p a r a r e t e r e s t i m a t e s on t h e b a s i s o f Monte CÍarlo e x p e r i m e n t f o r t h e c h o s e n l i n e a r m o d e l s a a s a n a r r o w s c o p e . O n ly a p i c t u r e o f b e h a v i o u r o f t h e c h o s e n

(10)

e s t i m a t i o n m e t h o d s u n d e r g i v e n e x p e r i m e n t c o n d i t i o n s w as o b t a i n -e d . To e v a l u a t e t h e e f f i c i e n c y o f t h e s e m e t h o d s i n a b r o a d s e n -s e , i t i -s n e c e -s -s a r y t o e n l a r g e t h e i n v e s t i g a t i o n s , f i r s t o f a l l , t o c o n s i d e r d i f f e r e n t n u m e r i c a l s t r u c t u r e s o f p a r a m e t e r s f o r t h e c h o s e n m o d e l s , g i v e n d i f f e r e n t d e g r e e s o f c o r r e l a t i o n o f c x n l a - n a t o r y v a r i a b l e s . I t w o u l d b e a d v i s a b l e t o c a r r y o u t e x p e r i m e n t s g i v e n l o w e r l e v e l s o f R2 c o e f f i c i e n t and h i g h e r l e v e l s c.f. PD. I n t h e m o d e l s w i t h a t l e a s t tw o v a r i a b l e s w i t h m e a s u r e m e n t e r r o r s , t i i e r e i s an a d d i t i o n a l p r o b l e m c a u s e d by t h e n e c e s s i t y o f t a k i n g i n t o a c c o u n t d i f f e r e n t v a r i a n t s o f r e l a t i o n s h i p s b e t w e e n t h e e r -r o -r s f o -r s e p a -r a t e v a r i a b l e s w h i l e a n a l y s i n g t h e p r o p e r t i e s o f t h e s e m e t h o d s . REFKRKNCĽS [i ] K l e p a c z H. (14 8 4), E fe k ty w n o ś ć m etod e s ty m a c j i m o d e li jo d n o ió w - naniow ych z b łęd a m i w zm ie n n y c h , d o c t o r t h e s i s , Łódź.

Í2J K l e p a c z H. (1984 ), p rzeg lą d metod e s ty m a c ji m odeli jcdnorówna- niowycn z błędna i w zm ienm jrb, Z e s z . Nauk. Akad. Ekon. , 181 (K raków ). [ 3 ] K l e p a ć z H . , The E ffi c ie n c y o f E stim a tio n Methods f o r Models

w ith E r r o r s in E xplanatory V a ria b le s, f o r t h c a n i n g . j

^4] Z i e l i ń s k i R. ( 1 9 7 2 ) , T a b lico s t a t y s t y c z n e , PWE, Warszawa.

H alina Klepacz

OBCIĄŻENIE ESTYMATORÓW PARAMETRÓW MODELI Z BŁĘDAMI W ZMIENNYCH OBJAŚNIAJĄCYCH

W artykuli- m a i i żuje s i ę w ie lk o ś c i obciążeń pflrametr<>w strukturalnych mo-d e li z mo-dwiema zmiennymi ob jaśniającymi, w tym jedna j e s t obarczona błędem po-miaru oraz z trzema zmiennymi, z których jedna lub dwie s# mierzone z b łę -dem, Analizę przeprowadza s i ę ze względu na metody e s ty m a c j i, w ielkość próby, poziom: współczynnika d eter m in a cji, błędu pomiaru i współczynnika k o r e l a c j i miedzy zmiennymi.

Cytaty

Powiązane dokumenty

zugs in Abhangigkeit von der Wasser- tiefe, die dann zu erwarten sind, wenn die Leistung statt auf zwei auf drei oder vier Propeller verteilt wird.

We- dług innych danych  (21,29) kierowcy z  wysokim po- ziomem lęku, zbadanym z  wykorzystaniem skali  X-2 Inwentarza Stanu i  Cechy Lęku, częściej niż osoby

W latach 1920-1939 w Toruniu działały następujące związki wyzna­ niowe2: Kościół rzymskokatolicki, Kościół ewangelicko-augsburski, Kościół ewangelicko-unijny,

spired by Polish master of painting Wacław Kondek, OFF Galleria Project by the Urban Forms Foundation, public art located in a private backyard, 12 Pogonowskiego Street, Lodz,

Miscytyzm, o którym tu mówimy, jest zupełnie innego rodzaju niż ten, który symbolizuje postacie św. Jana od Krzyża czy św. Jest to raczej mistycyzm Plotyński, z tą

Tomasz Kubalica , dr, adiunkt w Zakładzie Historii Filozofii No- wożytnej i Współczesnej Instytutu Filozofii Uniwersytetu Śląskiego.... Akademii Pomorskiej w Słupsku, kierownik

of differences in spatial diversification of economic potential in the statistical central region (NTS 1) and to refer the results of the research to the concept of